Files
FabledCurator/agent/fc_agent/worker.py
T
bvandeusen 4a1a9ec5a7
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 18s
CI / backend-lint-and-test (push) Successful in 27s
CI / integration (push) Successful in 3m25s
feat(agent): GPU load readout + live worker-count tuning (#114)
Control UI gains what the operator asked for:
- GPU load (nvidia-smi): util %, VRAM used/total + bar, temp — so you can see how
  hard the card is working while you're at the desktop.
- Worker count is now a live − / + control (POST /concurrency), not just an env:
  the worker is a pool of independent slots (shared model, so slots add concurrent
  inference, not N× VRAM). Dial up for speed, down to free the card. Replaces
  pause/resume with Start/Stop + the worker dial.
- Graceful release on stop / pool-shrink: a slot hands its still-leased jobs back
  via client.release() so they're re-picked immediately (pairs with the server
  recovery sweep).

Not CI-tested (agent/ outside CI) — verified by running.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
2026-06-29 19:07:40 -04:00

153 lines
5.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""The lease → fetch → detect+embed → submit loop, run by a pool of worker
slots whose count is tunable live from the UI.
Each slot is an independent loop (its own leases; the server's SKIP-LOCKED lease
keeps them from colliding). More slots = more GPU load + throughput; the model is
loaded once and shared, so slots add concurrent inference, not N× model VRAM.
That's the dial the operator turns to trade desktop responsiveness for speed.
Stop (or shrinking the pool) RELEASES a slot's still-leased jobs immediately so
orphaned work is re-picked at once rather than waiting out the lease.
"""
import threading
import time
from . import media, models
from .client import FcClient
from .config import Config
from .crops import crop_region
MAX_CONCURRENCY = 8
class _Slot:
"""One worker loop. `inflight` = jobs leased but not yet processed, so a
graceful stop can hand them back."""
__slots__ = ("stop", "inflight")
def __init__(self):
self.stop = threading.Event()
self.inflight: list[int] = []
class Worker:
def __init__(self, cfg: Config):
self.cfg = cfg
self.client = FcClient(cfg.fc_url, cfg.token, cfg.agent_id)
self._lock = threading.Lock()
self._running = False
self._target = max(1, min(MAX_CONCURRENCY, cfg.concurrency))
self._slots: list[_Slot] = []
self.processed = 0
self.errors = 0
self._active = 0 # slots currently mid-image
# --- control -----------------------------------------------------------
def start(self):
with self._lock:
self._running = True
self._reconcile_locked()
def stop(self):
with self._lock:
self._running = False
slots, self._slots = self._slots, []
for s in slots:
s.stop.set() # each slot releases its inflight on exit
def set_concurrency(self, n: int):
with self._lock:
self._target = max(1, min(MAX_CONCURRENCY, int(n)))
if self._running:
self._reconcile_locked()
def _reconcile_locked(self):
while len(self._slots) < self._target:
slot = _Slot()
self._slots.append(slot)
threading.Thread(target=self._loop, args=(slot,), daemon=True).start()
while len(self._slots) > self._target:
self._slots.pop().stop.set()
def status(self) -> dict:
with self._lock:
return {
"state": "running" if self._running else "stopped",
"concurrency": self._target,
"workers": len(self._slots),
"active": self._active,
"processed": self.processed,
"errors": self.errors,
}
def _bump(self, *, processed=0, errors=0, active=0):
with self._lock:
self.processed += processed
self.errors += errors
self._active += active
# --- per-slot loop -----------------------------------------------------
def _loop(self, slot: _Slot):
while not slot.stop.is_set() and self._running:
try:
jobs = self.client.lease(self.cfg.batch_size)
except Exception:
time.sleep(self.cfg.poll_idle_seconds)
continue
if not jobs:
time.sleep(self.cfg.poll_idle_seconds)
continue
slot.inflight = [j["job_id"] for j in jobs]
for job in jobs:
if slot.stop.is_set() or not self._running:
break
self._process(job)
slot.inflight = [i for i in slot.inflight if i != job["job_id"]]
if slot.inflight:
self.client.heartbeat(slot.inflight)
# Graceful hand-back of anything leased but not processed.
if slot.inflight:
self.client.release(slot.inflight)
slot.inflight = []
def _process(self, job: dict):
self._bump(active=1)
try:
data = self.client.fetch_image(job["image_url"])
if media.is_video(job.get("mime", "")):
frames = media.sample_frames(
data, job.get("frame_interval_seconds", 4.0),
job.get("max_frames", 64),
) or [(None, media.load_image(data))]
else:
frames = [(None, media.load_image(data))]
regions = []
ev = self.cfg.ccip_model or "ccip-default"
dv = f"person-{self.cfg.detector_level}"
for t, frame in frames:
figs = models.detect_figures(frame, self.cfg.detector_level)
if not figs:
figs = [((0.0, 0.0, 1.0, 1.0), None)] # whole-frame fallback
for bbox, score in figs:
crop = crop_region(frame, bbox)
if crop is None:
continue
vec = models.ccip_vector(crop, self.cfg.ccip_model or None)
regions.append({
"kind": "figure",
"bbox": list(bbox),
"frame_time": t,
"score": score,
"ccip_embedding": vec,
"embedding_version": ev,
"detector_version": dv,
})
self.client.submit(job["job_id"], regions, ["figure", "face"])
self._bump(processed=1)
except Exception as exc: # noqa: BLE001 — report + move on
self._bump(errors=1)
self.client.fail(job["job_id"], str(exc)[:500])
finally:
self._bump(active=-1)